No description available.

No description available.

No description available.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第21208号 / 情博第661号 / 新制||情||114(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 美濃 導彦, 教授 河原 達也, 教授 中村 裕一 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

No description available.

PET imaging is a key tool in the fight against cancer. One of the main issues of PET imaging is the high level of noise that characterizes the reconstructed image, during this project we implemented several algorithms with the aim of improving the reconstruction of PET images exploiting the power of Neural Networks. First, we developed a simple denoiser that improves the quality of an image that has already been reconstructed with a reconstruction algorithm like the Maximum Likelihood Expectation Maximization. Then we implemented two Neural Network based iterative reconstruction algorithms that reconstruct directly an image starting from the measured data rearranged into sinograms, thus removing the dependence of the reconstruction result from the initial reconstruction needed by the denoiser. Finally, we used the most promising approach, among the developed ones, to reconstruct images from data acquired with the KTH MTH microCT - miniPET.

No description available.

The undirected graphical model or Markov Random Field (MRF) is one of the more popular models used in computer vision and is the type of model with which this work is concerned. Models based on these methods have proven to be particularly useful in low-level vision systems and have led to state-of-the-art results for MRF-based systems. The research presented will describe a new discriminative training algorithm and its implementation. The MRF model will be trained by optimizing its parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. While previous work has relied on time-consuming iterative approximations or stochastic approximations, this work will demonstrate how implicit differentiation can be used to analytically differentiate the overall training loss with respect to the MRF parameters. This framework leads to an efficient, flexible learning algorithm that can be applied to a number of different models. The effectiveness of the proposed learning method will then be demonstrated by learning the parameters of two related models applied to the task of denoising images. The experimental results will demonstrate that the proposed learning algorithm is comparable and, at times, better than previous training methods applied to the same tasks. A new segmentation model will also be introduced and trained using the proposed learning method. The proposed segmentation model is based on an energy minimization framework that is iii novel in how it incorporates priors on the size of the segments in a way that is straightforward to implement. While other methods, such as normalized cuts, tend to produce segmentations of similar sizes, this method is able to overcome that problem and produce more realistic segmentations.

In this paper we outline a novel method for training a generative adversarial network based denoising model from an exclusively corrupted and unpaired dataset of images. Our model can learn without clean data or corrupted image pairs, and instead only requires that the noise distribution is able to be expressed analytically and that the noise at each pixel is independent. We utilize maximum a posteriori estimation as the underlying solution framework, optimizing over the analytically expressed noise generating distribution as the likelihood and employ the GAN as the prior. We then evaluate our method on several popular datasets of varying size and levels of corruption. Further we directly compare the numerical results of our experiments to that of the current state of the art unsupervised denoising model. While our proposed approach's experiments do not achieve a new state of the art, it provides an alternative method to unsupervised denoising and shows strong promise as an area for future research and untapped potential.

Pulse-shaped signals require a tool that can accurately analyse and identify the peak characteristics in the spectrum. One recently developed tool available to analyse non-stationary pulse-shaped waveforms with a suitable peak reconstruction is semiclassical signal analysis (SCSA). SCSA is a signal representation method that decomposes a real positive signal y(t) into a set of squared eigenfunctions through the discrete spectrum of the Schr¨odinger operator. In this study, we apply SCSA in two directions. First, we propose a new signal denoising method based on the signal curvature. We use this technique to show that denoising the pulse-shaped signal by regularizing its curvature can yield better peak-preserving performance than traditional filters, such as moving average filter or wavelet. Second, we apply SCSA to biomedical signal analysis. The localization abilities of L2 normalized squared eigenfunctions are used in blood pressure (BP) estimation. Based on existing properties, the systolic and diastolic phases are separated into photoplethysmograms (PPGs), which are then used as features for BP estimation. In addition, the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC II) database is used to test the application with more than 8000 subjects. Another application uses SCSA features to characterize EEG and MEG signals, leading to more accurate epileptic spike detection and diagnosis in epileptic patients. Both applications are validated using real datasets, which guarantees statistical reliability and motivates future work of this model in clinical applications and equipment designs.